Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    round, square, above

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    醌
    0.43
    alamualaikum
    0.42
    面に
    0.42
    麵
    0.42
    <unused36>
    0.41
     सीमाओं
    0.41
    distributions
    0.40
     کمپیو
    0.40
    ▀
    0.40
    чений
    0.39
    POSITIVE LOGITS
    Round
    0.46
     Round
    0.46
     round
    0.45
     CD
    0.42
     Atom
    0.40
     Row
    0.39
     Mog
    0.38
     cl
    0.38
    ROUND
    0.37
     Rond
    0.37
    Act Density 0.000%

    No Known Activations